pubid 2.0.9 → 2.0.11

data/lib/pubid/omg/pubid_urn_schema.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Omg
+    # The pubid-scheme URN of OMG (issue #670; docs/URN-SCHEMES.adoc).
+    #
+    #   OMG AMI4CCM 1.0  ->  urn:pubid:omg:spec:acronym-AMI4CCM:v-1.0
+    #
+    # No positional core: an OMG specification names itself by its acronym.
+    # The current urn:omg:… form of #to_urn is pubid-invented and stays
+    # there.
+    PubidUrnSchema = Pubid::PubidUrn.define("omg") do
+      atom "part", "part"
+      atom "version", "v"
+      atom "acronym", "acronym"
+
+      type "pubid:omg:identifier", "id", core: []
+      type "pubid:omg:specification", "spec", core: []
+    end
+  end
+end

data/lib/pubid/omg.rb

@@ -17,6 +17,7 @@ module Pubid
     autoload :Identifiers, "#{__dir__}/omg/identifiers"
     autoload :Parser, "#{__dir__}/omg/parser"
     autoload :Renderer, "#{__dir__}/omg/renderer"
+    autoload :PubidUrnSchema, "#{__dir__}/omg/pubid_urn_schema"
 
     def self.parse(identifier)
       Identifier.parse(identifier)

data/lib/pubid/sae/pubid_urn_schema.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Sae
+    # The pubid-scheme URN of SAE (issue #670; docs/URN-SCHEMES.adoc).
+    #
+    #   SAE J3016_202104  ->  urn:pubid:sae:id:3016:typeabbr-J:year-2021:month-4
+    #
+    # The current urn:sae:… form of #to_urn is pubid-invented and stays
+    # there. The type (`J`, `AS`, `ARP`, `AMS`) is an atom, because the
+    # identifier type is one class carrying every series code; the date
+    # fields are Integers.
+    PubidUrnSchema = Pubid::PubidUrn.define("sae") do
+      atom "type.abbr", "typeabbr"
+      atom "revision", "rev"
+      atom "amendment", "amd"
+      atom "date.year", "year", kind: :int
+      atom "date.month", "month", kind: :int
+
+      type "pubid:sae:identifier", "id"
+    end
+  end
+end

data/lib/pubid/sae.rb

@@ -17,6 +17,7 @@ module Pubid
     autoload :Renderer, "#{__dir__}/sae/renderer"
     autoload :UrnGenerator, "#{__dir__}/sae/urn_generator"
     autoload :UrnParser, "#{__dir__}/sae/urn_parser"
+    autoload :PubidUrnSchema, "#{__dir__}/sae/pubid_urn_schema"
 
     def self.parse(input)
       Identifier.parse(input)

data/lib/pubid/tgpp/pubid_urn_schema.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Tgpp
+    # The pubid-scheme URN of 3GPP (issue #670; docs/URN-SCHEMES.adoc).
+    #
+    #   TS 01.01:REL-96/5.0.0  ->  urn:pubid:3gpp:ts:01.01:part-01:release-96:v-5.0.0
+    #
+    # The official urn:3gpp: namespace (RFC 5279) stays on #to_urn. The
+    # parts ("01.01" splits to part "01" and part "01"…) are the list the
+    # flavor models; the release and the version close the URN.
+    PubidUrnSchema = Pubid::PubidUrn.define("3gpp") do
+      atom "parts", "part", kind: :list
+      atom "version", "v"
+      atom "release", "release"
+      atom "suffix", "suffix"
+
+      type "pubid:3gpp:identifier", "id"
+      type "pubid:3gpp:technical-report", "tr"
+      type "pubid:3gpp:technical-specification", "ts"
+    end
+  end
+end

data/lib/pubid/tgpp.rb

@@ -34,6 +34,7 @@ module Pubid
     autoload :Renderer, "#{__dir__}/tgpp/renderer"
     autoload :UrnGenerator, "#{__dir__}/tgpp/urn_generator"
     autoload :UrnParser, "#{__dir__}/tgpp/urn_parser"
+    autoload :PubidUrnSchema, "#{__dir__}/tgpp/pubid_urn_schema"
 
     # Parse a 3GPP identifier string
     def self.parse(identifier)

data/lib/pubid/un/pubid_urn_schema.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Un
+    # The pubid-scheme URN of UN (issue #670; docs/URN-SCHEMES.adoc).
+    #
+    #   A/RES/78/1  ->  urn:pubid:un:document:A,RES,78:1
+    #
+    # The path segments are the list before the final number; the number is
+    # the positional core. The current urn:un:… form of #to_urn is
+    # pubid-invented and stays there.
+    PubidUrnSchema = Pubid::PubidUrn.define("un") do
+      atom "path", "path", kind: :list
+
+      type "pubid:un:document", "document"
+      type "pubid:un:identifier", "id"
+    end
+  end
+end

data/lib/pubid/un.rb

@@ -12,6 +12,7 @@ module Pubid
     autoload :Identifiers, "#{__dir__}/un/identifiers"
     autoload :Parser, "#{__dir__}/un/parser"
     autoload :Renderer, "#{__dir__}/un/renderer"
+    autoload :PubidUrnSchema, "#{__dir__}/un/pubid_urn_schema"
 
     def self.parse(identifier)
       Identifier.parse(identifier)

data/lib/pubid/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Pubid
-  VERSION = "2.0.9"
+  VERSION = "2.0.11"
 end

data/lib/pubid/w3c/pubid_urn_schema.rb

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+module Pubid
+  module W3c
+    # The pubid-scheme URN of w3c (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    # Declared from the doc's section: the atom, facet and type tables
+    # below are the doc's design, conforming token-for-token.
+    PubidUrnSchema = Pubid::PubidUrn.define("w3c") do
+      atom "date", "date"
+
+
+      type "pubid:w3c:candidate-recommendation", "cr"
+      type "pubid:w3c:candidate-recommendation-draft", "crd"
+      type "pubid:w3c:draft-note", "dn"
+      type "pubid:w3c:identifier", "id"
+      type "pubid:w3c:note", "note"
+      type "pubid:w3c:obsolete-recommendation", "or"
+      type "pubid:w3c:proposed-edited-recommendation", "per"
+      type "pubid:w3c:proposed-recommendation", "pr"
+      type "pubid:w3c:recommendation", "rec"
+      type "pubid:w3c:standard", "std"
+      type "pubid:w3c:superseded-recommendation", "sr"
+      type "pubid:w3c:working-draft", "wd"
+    end
+  end
+end

data/lib/pubid/w3c.rb

@@ -16,6 +16,7 @@ module Pubid
     autoload :Renderer, "#{__dir__}/w3c/renderer"
     autoload :UrnGenerator, "#{__dir__}/w3c/urn_generator"
     autoload :UrnParser, "#{__dir__}/w3c/urn_parser"
+    autoload :PubidUrnSchema, "#{__dir__}/w3c/pubid_urn_schema"
 
     # Parse a W3C identifier string
     def self.parse(identifier)

data/lib/pubid/xsf/pubid_urn_schema.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Xsf
+    # The pubid-scheme URN of xsf (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    # Declared from the doc's section: the atom, facet and type tables
+    # below are the doc's design, conforming token-for-token.
+    PubidUrnSchema = Pubid::PubidUrn.define("xsf") do
+      type "pubid:xsf:identifier", "id"
+      type "pubid:xsf:xep", "xep"
+    end
+  end
+end

data/lib/pubid/xsf.rb

@@ -21,6 +21,7 @@ module Pubid
     autoload :Renderer, "#{__dir__}/xsf/renderer"
     autoload :UrnGenerator, "#{__dir__}/xsf/urn_generator"
     autoload :UrnParser, "#{__dir__}/xsf/urn_parser"
+    autoload :PubidUrnSchema, "#{__dir__}/xsf/pubid_urn_schema"
 
     # Parse an XSF identifier string
     def self.parse(identifier)

data/lib/pubid.rb

@@ -238,6 +238,7 @@ module Pubid
   # @param format [Symbol] :auto, :human, :mr_string, or :urn
   # @return [Identifier] The parsed identifier
   # @raise [ArgumentError] for a non-String, or one over {MAX_INPUT_LENGTH}
+  #   (as {Errors::InvalidInputError}, which is one)
   # @raise [Pubid::Errors::ParseError] when no flavor can parse the string — the
   #   class every flavor's own +parse+ raises (see the parse-failure contract)
   def self.parse(string, format: :auto)
@@ -249,6 +250,15 @@ module Pubid
       raise Pubid::Errors::InvalidInputError,
             Pubid::INPUT_TOO_LONG_MESSAGE
     end
+    # Invalid encoding is bad input, not a grammar failure: the detectors
+    # and normalization regexes raise raw `ArgumentError` (invalid byte
+    # sequence) or `Encoding::CompatibilityError` on it, which is the leak
+    # the contract closes (issue #670). The bytes are read as UTF-8 — a
+    # binary string of ASCII bytes (".b") is fine, high bytes are not.
+    unless string.dup.force_encoding(Encoding::UTF_8).valid_encoding?
+      raise Pubid::Errors::InvalidInputError,
+            "input string has invalid encoding"
+    end
 
     format = FormatDetector.detect(string) if format == :auto
 
@@ -282,22 +292,38 @@ module Pubid
   #
   # @param string [String] the URN
   # @return [Identifier] the parsed identifier
+  # @raise [Pubid::Errors::InvalidInputError] for a non-String
   #
   # A pubid-scheme URN ("urn:pubid:…", see {PubidUrn}) is decoded by the
   # shared codec; every other namespace goes to its flavor's UrnParser.
+  # Every decode failure on this surface is a pubid error (issue #670): an
+  # empty string, a missing or unknown namespace, invalid encoding, and a
+  # URN a flavor's parser rejects all raise {Errors::UrnParseError} — the
+  # raw `ArgumentError` the detection and the flavor parsers raise is the
+  # wrapped failure's cause, never the raised class.
   def self.parse_urn(string)
+    unless string.is_a?(String)
+      raise Pubid::Errors::InvalidInputError,
+            Pubid::INPUT_NOT_A_STRING_MESSAGE
+    end
     eager_load_flavors!
     return PubidUrn.parse(string) if PubidUrn.pubid_urn?(string)
 
     flavor = detect_flavor_from_urn(string)
     flavor_module = Registry.get(flavor)
     unless flavor_module
-      raise ArgumentError,
-            "Unknown flavor in URN: #{flavor}"
+      raise Errors::UrnParseError,
+            "unknown URN namespace: #{flavor.inspect} (in #{string.inspect})"
     end
 
     urn_parser = flavor_module.const_get(:UrnParser)
     urn_parser.parse(string)
+  rescue Errors::Error
+    raise
+  rescue StandardError => e
+    raise Errors::UrnParseError,
+          "URN #{string.inspect} does not parse as #{flavor.inspect}: #{e.message}",
+          cause: e
   end
 
   # The slug form (relaton#441): the pubid-scheme URN of +source+ in

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pubid
 version: !ruby/object:Gem::Version
-  version: 2.0.9
+  version: 2.0.11
 platform: ruby
 authors:
 - Ribose Inc.
@@ -142,6 +142,7 @@ files:
 - lib/pubid/adobe/identifiers/publication.rb
 - lib/pubid/adobe/identifiers/tech_note.rb
 - lib/pubid/adobe/parser.rb
+- lib/pubid/adobe/pubid_urn_schema.rb
 - lib/pubid/adobe/renderer.rb
 - lib/pubid/adobe/urn_generator.rb
 - lib/pubid/adobe/urn_parser.rb
@@ -157,6 +158,7 @@ files:
 - lib/pubid/amca/identifiers/publication.rb
 - lib/pubid/amca/identifiers/standard.rb
 - lib/pubid/amca/parser.rb
+- lib/pubid/amca/pubid_urn_schema.rb
 - lib/pubid/amca/renderer.rb
 - lib/pubid/amca/single_identifier.rb
 - lib/pubid/amca/urn_generator.rb
@@ -265,6 +267,7 @@ files:
 - lib/pubid/bipm/identifiers/metrologia_article.rb
 - lib/pubid/bipm/identifiers/si_brochure.rb
 - lib/pubid/bipm/parser.rb
+- lib/pubid/bipm/pubid_urn_schema.rb
 - lib/pubid/bipm/renderer.rb
 - lib/pubid/bipm/urn_generator.rb
 - lib/pubid/bipm/urn_parser.rb
@@ -313,6 +316,7 @@ files:
 - lib/pubid/bsi/identifiers/value_added_publication.rb
 - lib/pubid/bsi/model.rb
 - lib/pubid/bsi/parser.rb
+- lib/pubid/bsi/pubid_urn_schema.rb
 - lib/pubid/bsi/renderer.rb
 - lib/pubid/bsi/single_identifier.rb
 - lib/pubid/bsi/urn_generator.rb
@@ -325,6 +329,7 @@ files:
 - lib/pubid/calconnect/identifiers.rb
 - lib/pubid/calconnect/identifiers/standard.rb
 - lib/pubid/calconnect/parser.rb
+- lib/pubid/calconnect/pubid_urn_schema.rb
 - lib/pubid/calconnect/renderer.rb
 - lib/pubid/calconnect/urn_generator.rb
 - lib/pubid/calconnect/urn_parser.rb
@@ -335,6 +340,7 @@ files:
 - lib/pubid/ccsds/identifiers/base.rb
 - lib/pubid/ccsds/identifiers/corrigendum.rb
 - lib/pubid/ccsds/parser.rb
+- lib/pubid/ccsds/pubid_urn_schema.rb
 - lib/pubid/ccsds/single_identifier.rb
 - lib/pubid/ccsds/supplement_identifier.rb
 - lib/pubid/ccsds/urn_generator.rb
@@ -384,6 +390,7 @@ files:
 - lib/pubid/cie/identifiers/supplement.rb
 - lib/pubid/cie/identifiers/tutorial_bundle.rb
 - lib/pubid/cie/parser.rb
+- lib/pubid/cie/pubid_urn_schema.rb
 - lib/pubid/cie/single_identifier.rb
 - lib/pubid/cie/supplement_identifier.rb
 - lib/pubid/cie/urn_generator.rb
@@ -431,6 +438,7 @@ files:
 - lib/pubid/csa/identifiers/series.rb
 - lib/pubid/csa/identifiers/standard.rb
 - lib/pubid/csa/parser.rb
+- lib/pubid/csa/pubid_urn_schema.rb
 - lib/pubid/csa/renderer.rb
 - lib/pubid/csa/single_identifier.rb
 - lib/pubid/csa/urn_generator.rb
@@ -442,6 +450,7 @@ files:
 - lib/pubid/doi/identifiers.rb
 - lib/pubid/doi/identifiers/resource.rb
 - lib/pubid/doi/parser.rb
+- lib/pubid/doi/pubid_urn_schema.rb
 - lib/pubid/doi/renderer.rb
 - lib/pubid/easc.rb
 - lib/pubid/easc/builder.rb
@@ -450,6 +459,7 @@ files:
 - lib/pubid/easc/identifiers/pmg.rb
 - lib/pubid/easc/identifiers/rmg.rb
 - lib/pubid/easc/parser.rb
+- lib/pubid/easc/pubid_urn_schema.rb
 - lib/pubid/easc/renderer.rb
 - lib/pubid/easc/urn_generator.rb
 - lib/pubid/easc/urn_parser.rb
@@ -462,6 +472,7 @@ files:
 - lib/pubid/ecma/identifiers/standard.rb
 - lib/pubid/ecma/identifiers/technical_report.rb
 - lib/pubid/ecma/parser.rb
+- lib/pubid/ecma/pubid_urn_schema.rb
 - lib/pubid/ecma/renderer.rb
 - lib/pubid/ecma/urn_generator.rb
 - lib/pubid/ecma/urn_parser.rb
@@ -493,6 +504,7 @@ files:
 - lib/pubid/evs/identifiers/international_adoption.rb
 - lib/pubid/evs/identifiers/national_adoption.rb
 - lib/pubid/evs/parser.rb
+- lib/pubid/evs/pubid_urn_schema.rb
 - lib/pubid/evs/renderer.rb
 - lib/pubid/evs/urn_generator.rb
 - lib/pubid/evs/urn_parser.rb
@@ -511,6 +523,7 @@ files:
 - lib/pubid/gb/identifiers/all_parts.rb
 - lib/pubid/gb/identifiers/standard.rb
 - lib/pubid/gb/parser.rb
+- lib/pubid/gb/pubid_urn_schema.rb
 - lib/pubid/gb/renderer.rb
 - lib/pubid/gost.rb
 - lib/pubid/gost/CLAUDE.md
@@ -544,6 +557,7 @@ files:
 - lib/pubid/iala/identifiers/resolution.rb
 - lib/pubid/iala/identifiers/standard.rb
 - lib/pubid/iala/parser.rb
+- lib/pubid/iala/pubid_urn_schema.rb
 - lib/pubid/iala/renderer.rb
 - lib/pubid/iala/urn_generator.rb
 - lib/pubid/iala/urn_parser.rb
@@ -554,6 +568,7 @@ files:
 - lib/pubid/iana/identifiers.rb
 - lib/pubid/iana/identifiers/registry.rb
 - lib/pubid/iana/parser.rb
+- lib/pubid/iana/pubid_urn_schema.rb
 - lib/pubid/iana/renderer.rb
 - lib/pubid/iana/urn_generator.rb
 - lib/pubid/iana/urn_parser.rb
@@ -569,6 +584,7 @@ files:
 - lib/pubid/idf/identifiers/international_standard.rb
 - lib/pubid/idf/identifiers/reviewed_method.rb
 - lib/pubid/idf/parser.rb
+- lib/pubid/idf/pubid_urn_schema.rb
 - lib/pubid/idf/renderer.rb
 - lib/pubid/idf/single_identifier.rb
 - lib/pubid/idf/supplement_identifier.rb
@@ -685,6 +701,7 @@ files:
 - lib/pubid/ietf/identifiers/serialization.rb
 - lib/pubid/ietf/identifiers/std.rb
 - lib/pubid/ietf/parser.rb
+- lib/pubid/ietf/pubid_urn_schema.rb
 - lib/pubid/ietf/renderer.rb
 - lib/pubid/ietf/urn_generator.rb
 - lib/pubid/ietf/urn_parser.rb
@@ -699,6 +716,7 @@ files:
 - lib/pubid/iho/identifiers/miscellaneous.rb
 - lib/pubid/iho/identifiers/publication.rb
 - lib/pubid/iho/identifiers/standard.rb
+- lib/pubid/iho/pubid_urn_schema.rb
 - lib/pubid/iho/renderer.rb
 - lib/pubid/iho/urn_generator.rb
 - lib/pubid/iho/urn_parser.rb
@@ -709,6 +727,7 @@ files:
 - lib/pubid/isbn/identifiers.rb
 - lib/pubid/isbn/identifiers/book.rb
 - lib/pubid/isbn/parser.rb
+- lib/pubid/isbn/pubid_urn_schema.rb
 - lib/pubid/isbn/renderer.rb
 - lib/pubid/iso.rb
 - lib/pubid/iso/CLAUDE.md
@@ -817,6 +836,7 @@ files:
 - lib/pubid/jis/identifiers/technical_specification.rb
 - lib/pubid/jis/identifiers/welding_engineering_standard.rb
 - lib/pubid/jis/parser.rb
+- lib/pubid/jis/pubid_urn_schema.rb
 - lib/pubid/jis/renderer.rb
 - lib/pubid/jis/single_identifier.rb
 - lib/pubid/jis/supplement_identifier.rb
@@ -887,6 +907,7 @@ files:
 - lib/pubid/oasis/identifiers.rb
 - lib/pubid/oasis/identifiers/standard.rb
 - lib/pubid/oasis/parser.rb
+- lib/pubid/oasis/pubid_urn_schema.rb
 - lib/pubid/oasis/renderer.rb
 - lib/pubid/oasis/urn_generator.rb
 - lib/pubid/oasis/urn_parser.rb
@@ -897,6 +918,7 @@ files:
 - lib/pubid/ogc/identifiers.rb
 - lib/pubid/ogc/identifiers/document.rb
 - lib/pubid/ogc/parser.rb
+- lib/pubid/ogc/pubid_urn_schema.rb
 - lib/pubid/ogc/renderer.rb
 - lib/pubid/ogc/urn_generator.rb
 - lib/pubid/ogc/urn_parser.rb
@@ -935,6 +957,7 @@ files:
 - lib/pubid/omg/identifiers.rb
 - lib/pubid/omg/identifiers/specification.rb
 - lib/pubid/omg/parser.rb
+- lib/pubid/omg/pubid_urn_schema.rb
 - lib/pubid/omg/renderer.rb
 - lib/pubid/parg.rb
 - lib/pubid/parg/artifact.rb
@@ -997,6 +1020,7 @@ files:
 - lib/pubid/sae/identifiers.rb
 - lib/pubid/sae/identifiers/base.rb
 - lib/pubid/sae/parser.rb
+- lib/pubid/sae/pubid_urn_schema.rb
 - lib/pubid/sae/renderer.rb
 - lib/pubid/sae/urn_generator.rb
 - lib/pubid/sae/urn_parser.rb
@@ -1015,6 +1039,7 @@ files:
 - lib/pubid/tgpp/identifiers/technical_report.rb
 - lib/pubid/tgpp/identifiers/technical_specification.rb
 - lib/pubid/tgpp/parser.rb
+- lib/pubid/tgpp/pubid_urn_schema.rb
 - lib/pubid/tgpp/renderer.rb
 - lib/pubid/tgpp/urn_generator.rb
 - lib/pubid/tgpp/urn_parser.rb
@@ -1025,6 +1050,7 @@ files:
 - lib/pubid/un/identifiers.rb
 - lib/pubid/un/identifiers/document.rb
 - lib/pubid/un/parser.rb
+- lib/pubid/un/pubid_urn_schema.rb
 - lib/pubid/un/renderer.rb
 - lib/pubid/urn_generator/base.rb
 - lib/pubid/urn_parser.rb
@@ -1050,6 +1076,7 @@ files:
 - lib/pubid/w3c/identifiers/superseded_recommendation.rb
 - lib/pubid/w3c/identifiers/working_draft.rb
 - lib/pubid/w3c/parser.rb
+- lib/pubid/w3c/pubid_urn_schema.rb
 - lib/pubid/w3c/renderer.rb
 - lib/pubid/w3c/urn_generator.rb
 - lib/pubid/w3c/urn_parser.rb
@@ -1060,6 +1087,7 @@ files:
 - lib/pubid/xsf/identifiers.rb
 - lib/pubid/xsf/identifiers/xep.rb
 - lib/pubid/xsf/parser.rb
+- lib/pubid/xsf/pubid_urn_schema.rb
 - lib/pubid/xsf/renderer.rb
 - lib/pubid/xsf/urn_generator.rb
 - lib/pubid/xsf/urn_parser.rb